© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37448
    Prev
    Next
    INDEX
    Explanations

    place names and suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    åľĨåľĨ
    -0.07
    ass
    -0.07
    ä¸¥æł¼è¦ģæ±Ĥèĩªå·±
    -0.07
    emic
    -0.07
    ÑĢÑį
    -0.07
    OMA
    -0.06
    ëĶĶìĸ´
    -0.06
    ненко
    -0.06
    夫妻æĦŁæĥħ
    -0.06
     ((_
    -0.06
    POSITIVE LOGITS
    eke
    0.08
    ExceptionHandler
    0.07
    åłĤ
    0.07
    ikov
    0.07
    emode
    0.07
    chnik
    0.07
    chia
    0.07
    iets
    0.07
    éĢĶ
    0.06
    िà¤ķ
    0.06
    Activations Density 3.016%

    No Known Activations